Abstract
Traditional speech emotion recognition (SER) eval-uations have been performed merely on a speaker-independent condition; some of them even did not evaluate their result on this condition. This paper highlights the importance of splitting training and test data for SER by script, known as sentence-open or text-independent criteria. The results show that em-ploying sentence-open criteria degraded the performance of SER. This finding implies the difficulties of recognizing emotion from speech in different linguistic information embedded in acoustic information. Surprisingly, text-independent criteria consistently performed worse than speaker+text-independent criteria. The full order of difficulties for splitting criteria on SER performances from the most difficult to the easiest is text-independent, speaker+text-independent, speaker-independent, and speaker+text-dependent, The gap between speaker+text-independent and text-independent was smaller than other criteria, strengthening the difficulties of recognizing emotion from sneech in different sentences.
| Original language | English |
|---|---|
| Title of host publication | TENCON 2021 - 2021 IEEE Region 10 Conference |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 760-764 |
| Number of pages | 5 |
| ISBN (Electronic) | 9781665495325 |
| DOIs | |
| Publication status | Published - 2021 |
| Externally published | Yes |
| Event | 2021 IEEE Region 10 Conference, TENCON 2021 - Auckland, New Zealand Duration: 7 Dec 2021 → 10 Dec 2021 |
Publication series
| Name | IEEE Region 10 Annual International Conference, Proceedings/TENCON |
|---|---|
| Volume | 2021-December |
| ISSN (Print) | 2159-3442 |
| ISSN (Electronic) | 2159-3450 |
Conference
| Conference | 2021 IEEE Region 10 Conference, TENCON 2021 |
|---|---|
| Country/Territory | New Zealand |
| City | Auckland |
| Period | 7/12/21 → 10/12/21 |
Keywords
- Speech emotion recognition
- data partition
- speaker-independent
- splitting criteria
- text-independent